The Comparison of Signature Verification Result Using 2DPCA Method and SSE Method

Anita Sindar R M Sinaga(1*),

(1) STMIK Penusa Medan
(*) Corresponding Author


The rate of speed and validation verify to be a reference of quality information and reliable results. Everyone has signature characteristics but it will be difficult to match original signatures with a clone. Two Dimensional Principal Component Analysis (2DPCA) method, Sum Equal Error (SSE) method includes a method that can provide accurate data verification value of 90% - 98%. Results of scanned signatures, converted from RGB image - grayscale - black white (binary color). The extraction process of each method requires experimental data as a data source in pixel size. Digital image consists of a collection of pixels then each image is converted in a matrix. Preprocessing Method 2 DPCA each data is divided into data planning and data testing. Extraction on SSE method, each data sought histogram value and total black value. This study yields a comparison of the suitability of the extraction results of each method. Both of these methods have a data accuracy rate of 97% - 98%. When compared to the results of the accuracy of image verification with 2DPCA method: SSE is 97%: 96%. With the same data source will be tested result of 2DPCA method with SSE method.


Pattern Recognition

Full Text:


Article Metrics

Abstract view : 55 times
PDF - 0 times


Qian Wang, Qian Gao, “IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops” pp. 1152-1158, 2016.

A. Mashhoori, M. Zolghadri Jahromi, “Block-wise two-directional 2DPCA with ensemble learning for face recognition”, pp. 111-117, 2013.

John Huguenard, “Stanford University School of Medicine,” 2015

Anita Sindar RMS, “Optical Systems and Digital Image Acquisition”, Juripol, pp. 61-60, 2018.

E. Jebamalar Leavline, D. Asir Antony Gnana Singh, “On Teaching Digital Image Processing with MATLAB”, American Journal of Signaling Processing, pp. 7-15, 2014.

Xiuhua Liang, Guangming Deng, Bin Yan, “Fruit and Vegetable Nutrition Value Assessment and Replacement Based on the Principal Component Analysis and Cluster Analysis,” Scientific Research Publishing, Applied Mathematics, pp. 1620-1629, 2016.

Shoichi Fujimori, Yu Kawakami, Masatoshi Kokubu, Wayne Rossman, Masaaki Umehara, Kotaro Yamada, “Entire Zero-Mean Curvature Graphs I Lorents-Minkowski 3-Space, The Quarterly Journal of Mathematics, pp. 801-837, 2016.

Santiago Velasco-Forero, Marcus Chen, Alvina Goh, “Comparative Analysis of Covariance Matrix Estimation for Anomaly Detection in Hyperspectral Image, IEEE Journal of Selected Topics in Signal Processing, pp.1061-1073, 2015.

Ivan Dokmanic, “Euclidean Distance Matrices: Essential Theory, Algorithms, and Applications”, IEEE Signal Processing Magazine, pp. 12-30, 2015.

Tippaya Thinsungnoen, Nuntawut Kaoungku, PangsakomDurongdumronchai, “The Clustering Validity with Silhouette and Sum of Squared Errors’, Proceedings of the 3rd International Conference on Industrial Application Engineering, pp.44-51, 2015.

Heri Nurdiyanto, Hermanto Hermanto, “Signature Recognition using Neural Network Probablisitc”, International Journal of Advances in Intelligent Informatics, Vol. 2, Issue 1, pp. 46-53, 2016

Heri Nurdiyanto, Putut Hasto Kuncoro, “Expert System for Measuring the Sugar-content in Sugarcane Using Forward Chaining Method”, ASEAN/Asian Academic Society International Conference Proceeding Series, Vol. 1, Issue 1, pp 79, 2016

Heri Nurdiyanto, Robbi Rahim, “Decision Support System for Electrical Power Selection to Household Users”, International Confrence of Science Infrastructure Technology and Regional Development, Vol.1, issue 1, pp 23, 2017


Copyright (c) 2018 International Journal of Artificial Intelligence Research


Organized by : Departemen Teknik Informatika STMIK Dharma Wacana
Published by : STMIK Dharma Wacana
Jl. Kenanga No.03 Mulyojati 16C Metro Barat Kota Metro Lampung
phone. +62725-7850671
Fax. +62725-7850671
Email: |

International Journal of artificial intelligence research

Creative Commons License
IJAIR is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.